{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P4PGKQ7OOD3RH5272GOIB45EHW","short_pith_number":"pith:P4PGKQ7O","schema_version":"1.0","canonical_sha256":"7f1e6543ee70f713f75fd19c80f3a43db7fe957bdbb76d60b7cb8fb8e7af61b0","source":{"kind":"arxiv","id":"2503.16867","version":2},"attestation_state":"computed","paper":{"title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaisi Guan, Kieran Liu, Meng Cao, Peng Zhang, Ruihua Song, Wei Liu, Yuchong Sun, Zhengfeng Lai","submitted_at":"2025-03-21T05:52:50Z","abstract_excerpt":"Precisely evaluating semantic alignment between text prompts and generated videos remains a challenge in Text-to-Video (T2V) Generation. Existing text-to-video alignment metrics like CLIPScore only generate coarse-grained scores without fine-grained alignment details, failing to align with human preference. To address this limitation, we propose ETVA, a novel Evaluation method of Text-to-Video Alignment via fine-grained question generation and answering. First, a multi-agent system parses prompts into semantic scene graphs to generate atomic questions. Then we design a knowledge-augmented mult"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.16867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-21T05:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"209acfdd3ae5ac5eab1b71881e82920e98aa4b3fa1d1e0922fe5590679986ba7","abstract_canon_sha256":"bc6649fcdbb3f04ac8cecc9c4f4eea586f95ef9923c4f6fb2f1ae8628921ee3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:45.531423Z","signature_b64":"BXRzkR1wKI11JqwVbfPaQ7CdzG0cBdZhFMhdR1nYmOFobzwJv41AFOhjQxS41HLTe90udkZZ80plLMeNmiBmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f1e6543ee70f713f75fd19c80f3a43db7fe957bdbb76d60b7cb8fb8e7af61b0","last_reissued_at":"2026-07-05T11:54:45.530832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:45.530832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaisi Guan, Kieran Liu, Meng Cao, Peng Zhang, Ruihua Song, Wei Liu, Yuchong Sun, Zhengfeng Lai","submitted_at":"2025-03-21T05:52:50Z","abstract_excerpt":"Precisely evaluating semantic alignment between text prompts and generated videos remains a challenge in Text-to-Video (T2V) Generation. Existing text-to-video alignment metrics like CLIPScore only generate coarse-grained scores without fine-grained alignment details, failing to align with human preference. To address this limitation, we propose ETVA, a novel Evaluation method of Text-to-Video Alignment via fine-grained question generation and answering. First, a multi-agent system parses prompts into semantic scene graphs to generate atomic questions. Then we design a knowledge-augmented mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16867","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.16867/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.16867","created_at":"2026-07-05T11:54:45.530905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16867v2","created_at":"2026-07-05T11:54:45.530905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16867","created_at":"2026-07-05T11:54:45.530905+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4PGKQ7OOD3R","created_at":"2026-07-05T11:54:45.530905+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4PGKQ7OOD3RH527","created_at":"2026-07-05T11:54:45.530905+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4PGKQ7O","created_at":"2026-07-05T11:54:45.530905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25361","citing_title":"HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00873","citing_title":"BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW","json":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW.json","graph_json":"https://pith.science/api/pith-number/P4PGKQ7OOD3RH5272GOIB45EHW/graph.json","events_json":"https://pith.science/api/pith-number/P4PGKQ7OOD3RH5272GOIB45EHW/events.json","paper":"https://pith.science/paper/P4PGKQ7O"},"agent_actions":{"view_html":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW","download_json":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW.json","view_paper":"https://pith.science/paper/P4PGKQ7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16867&json=true","fetch_graph":"https://pith.science/api/pith-number/P4PGKQ7OOD3RH5272GOIB45EHW/graph.json","fetch_events":"https://pith.science/api/pith-number/P4PGKQ7OOD3RH5272GOIB45EHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/action/storage_attestation","attest_author":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/action/author_attestation","sign_citation":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/action/citation_signature","submit_replication":"https://pith.science/pith/P4PGKQ7OOD3RH5272GOIB45EHW/action/replication_record"}},"created_at":"2026-07-05T11:54:45.530905+00:00","updated_at":"2026-07-05T11:54:45.530905+00:00"}